English
Related papers

Related papers: Sparse is Enough in Scaling Transformers

200 papers

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky

The energy consumption of large-scale ML models is dominated by data movement, shuffling billions of parameters across memory hierarchies and data centers. Sparsification offers a principled way to mitigate these costs by pruning redundant…

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in…

Machine Learning · Computer Science 2025-06-03 Sameera Ramasinghe , Thalaiyasingam Ajanthan , Gil Avraham , Yan Zuo , Alexander Long

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haowei Zhu , Ji Liu , Ziqiong Liu , Dong Li , Junhai Yong , Bin Wang , Emad Barsoum

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders…

Machine Learning · Computer Science 2024-06-07 Leo Gao , Tom Dupré la Tour , Henk Tillman , Gabriel Goh , Rajan Troll , Alec Radford , Ilya Sutskever , Jan Leike , Jeffrey Wu

Overparameterized neural networks generalize well but are expensive to train. Ideally, one would like to reduce their computational cost while retaining their generalization benefits. Sparse model training is a simple and promising approach…

Machine Learning · Computer Science 2022-05-12 Tri Dao , Beidi Chen , Kaizhao Liang , Jiaming Yang , Zhao Song , Atri Rudra , Christopher Ré

Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with…

Machine Learning · Computer Science 2022-04-12 Daniel Becking , Heiner Kirchhoffer , Gerhard Tech , Paul Haase , Karsten Müller , Heiko Schwarz , Wojciech Samek

Efficient solutions of large-scale, ill-conditioned and indefinite algebraic equations are ubiquitously needed in numerous computational fields, including multiphysics simulations, machine learning, and data science. Because of their…

Mathematical Software · Computer Science 2026-05-25 Xiaoye Sherry Li , Yang Liu

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Computation and Language · Computer Science 2022-01-25 Hongyu Gong , Xian Li , Dmitriy Genzel

We introduce a new balanced assignment of experts (BASE) layer for large language models that greatly simplifies existing high capacity sparse layers. Sparse layers can dramatically improve the efficiency of training and inference by…

Computation and Language · Computer Science 2021-04-01 Mike Lewis , Shruti Bhosale , Tim Dettmers , Naman Goyal , Luke Zettlemoyer

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Computer Vision and Pattern Recognition · Computer Science 2017-12-12 Dimitrios C. Gklezakos , Rajesh P. N. Rao

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or first-order (set-input) permutation invariant MLPs. Then,…

Machine Learning · Computer Science 2022-01-25 Jinwoo Kim , Saeyoon Oh , Seunghoon Hong

Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising. Its applicability to large datasets has been addressed with online and randomized…

Machine Learning · Statistics 2017-11-15 Arthur Mensch , Julien Mairal , Bertrand Thirion , Gaël Varoquaux

Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that…

Machine Learning · Computer Science 2026-03-24 Tasmay Pankaj Tibrewal , Pritish Saha , Ankit Meda , Kunal Singh , Pradeep Moturi

Large Transformers have achieved state-of-the-art performance across many tasks. Most open-source libraries on scaling Transformers focus on improving training or inference with better parallelization. In this work, we present TorchScale,…

Machine Learning · Computer Science 2022-11-24 Shuming Ma , Hongyu Wang , Shaohan Huang , Wenhui Wang , Zewen Chi , Li Dong , Alon Benhaim , Barun Patra , Vishrav Chaudhary , Xia Song , Furu Wei

Sparse representations using data dictionaries provide an efficient model particularly for signals that do not enjoy alternate analytic sparsifying transformations. However, solving inverse problems with sparsifying dictionaries can be…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Vishwanath Saragadam , Xin Li , Aswin Sankaranarayanan

Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time. The student models are typically compact transformers with fewer parameters, while expensive…

Computation and Language · Computer Science 2022-07-26 Qinyuan Ye , Madian Khabsa , Mike Lewis , Sinong Wang , Xiang Ren , Aaron Jaech